Quantifying uncertainties in the estimation of safety parameters by using bootstrapped artificial neural networks

Annals of Nuclear Energy

Volumn 35, Issue 12, 2008, Pages 2338-2350

  Secchi, Piercesare ^a   Zio, Enrico ^a   Di Maio, Francesco ^a  

^a POLITECNICO DI MILANO   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

BACKPROPAGATION; ELECTRIC FAULT LOCATION; ELECTRIC POWER PLANTS; LAWS AND LEGISLATION; MODAL ANALYSIS; NUCLEAR ENERGY; NUCLEAR FUEL CLADDING; NUCLEAR INDUSTRY; NUCLEAR POWER PLANTS; NUCLEAR PROPULSION; NUCLEAR REACTORS; POWER PLANTS; REGRESSION ANALYSIS;

ANALYTICAL MODELS; ARTIFICIAL NEURAL NETWORKS; CONFIDENCE INTERVALS; FUEL CLADDINGS; GROUP DISTRIBUTION HEADERS; MODEL DESCRIPTIONS; NUMEROUS MODELS; PARAMETRIC APPROACHES; PLANT MODELS; PLANT SAFETIES; REGRESSION MODELS; REGULATORY AUTHORITIES; SAFETY CASES; SAFETY MARGINS; SAFETY PARAMETERS;

NEURAL NETWORKS;

EID: 55949114387     PISSN: 03064549     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.anucene.2008.07.010     Document Type: Article

References (33)

1. Apostolakis G.E. The concept of probability in safety assessments of technological systems. Science (1990) 1359-1364
2. Bishop C.M. Neural Networks for Pattern Recognition (1995), Oxford University Press
3. Cadini F., Zio E., Kopustinskas V., and Urbonas R. An empirical model based on bootstrapped neural networks for computing the maximum fuel cladding temperature in a RBMK-1500 nuclear reactor accident. Nuclear Engineering and Design 238 (2008) 2165-2172
4. Dybowski R., and Roberts S.J. Confidence and prediction intervals for feed-forward neural networks. In: Dybowski R., and Gant V. (Eds). Clinical Applications of Artificial Neural Networks (2000), Cambridge University Press
5. Efron B. Bootstrap methods: another look at the Jacknife. Annals of Statistics 7 (1979) 1-26
6. Efron B., and Tibshirani R.J. An Introduction to the Bootstrap. Monographs on Statistics and Applied Probability 57 (1993), Chapman and Hall, New York
7. Fortin M.J., Jacquez G.M., and Shipley B. Computer-intensive methods. In: El-Shaarawi A., and Piegorsch (Eds). Enyclopedia of Environmetrics vol. I (2002), John Wiley & Sons, Ltd., Chichester 399-402
8. Gavrilas, M., Meyer, J., Youngblood, B., Prelewicz, D., Beaton, R., 2004. A generalized framework for assessment of safety margins in nuclear power plants. In: Proceedings to BE 2004: International Meeting on Updates in Best Estimate Methods in Nuclear Installations Safety Analysis, Washington, DC, November 14-18.
9. Guba A., Makai M., and Pál L. Statistical aspects of best estimate method-1. Reliability Engineering and System Safety 80 (2003) 217-232
10. Hastie T.J., Tibshirani R., and Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2001), Springer 533 p
11. Helton, J.C., 2004. Alternative Representations of Epistemic Uncertainty. Reliability Engineering and System Safety 85 (special issue).
12. Kaliatka A., Vaišnoras M., and Vileiniškis V. Best estimate analysis of group distribution header blockage events in RBMK-1500 reactors. Kerntechnik 70 (2005) 270-276
13. Kendall M., and Stuart A. The Advanced Theory of Statistics vol. 2 (1979), Charles Griffin, London
14. Kopustinskas, V., Urbonas, R., Kaliakta, A., Bolado-Lavin, R., 2005. Input parameters distribution sensitivity study of RBMK-1500 reactor one group distribution header complete blockage scenario. In: Advances in Safety and Reliability: Conference ESREL 2005. TriCity (Gdynia-Sopot-Gdansk), Poland, June 27-30, pp. 1125-1132.
15. Lilliefors H. On the Kolmogorov-Smirnov test for normality with mean and variance unknown. Journal of the American Statistical Association 62 (1967) 399-402
16. Martorell, S., 2007. Private communication.
17. Mitchell T. Machine Learning (1997), McGraw Hill
18. Muller B., and Reinhardt J. Neural Networks - An Introduction (1991), Springer-Verlag, New York
19. Nutt W.T., and Wallis G.B. Evaluation of nuclear safety from the outputs of computer codes in the presence of uncertainties. Reliability Engineering and System Safety 83 (2004) 57-77
20. Pál, L., Makai, M., 2002. Remarks on statistical aspects of safety analysis of complex systems. arXiv:physics/0308086v2.
21. Rumelhart D.E., and McClelland J.L. Parallel Distributed Processing 1 (1986), MIT Press, Cambridge, MA
22. Snedecor G.W., and Cochran W.G. Statistical Methods. seventh ed. (1980), Iowa State Press, Ames, IA pp. 175-178
23. Stuart G., Bienenstock E., and Doursat R. Neural networks and the bias/variance dilemma. Neural Computation 4 (1992) 1-58
24. Tibshirani R. A comparison of some error estimates for neural network models. Neural Computations 8 (1996) 152-163
25. Twomey J.M., and Smith A.E. Bias and variance of validation methods for function approximation neural networks under conditions of sparse data. IEEE Transaction on Systems, Man, and Cybernetics - Part C: Applications and Reviews 28 3 (1998) 417-430
26. Urbonas R., Kaliatka A., and Ušpuras E. Comparison of modern analysis approaches based on the postulated GDH blockage event at Ignalina NPP. Energetika 2 (2003) 14-21
27. Urbonas R., Uspuras E., and Kaliakta A. State-of-the-art computer code RELAP5 validation with RBMK-related separate phenomena data. Nuclear Engineering and Design 205 (2003) 65-81
28. Ušpuras E., and Kaliatka A. Accident and transient processes at NPPs with channel-type reactors. Monograph. Vol. 29 of Thermophysics (2006), Lithuanian Energy Institute, Kaunas
29. Wallis G.B. Evaluating the probability that the outputs of a computer code with random inputs will meet a set of evaluation criteria. Reliability Engineering and System Safety 91 (2006)
30. Wilks S.S. Determination of sample sizes for setting tolerance limits. Annals of Mathematical Statistics 12 (1941) 91-96
31. Wilks S.S. Statistical prediction with special reference to the problem of tolerance limits. Annals of Mathematical Statistics 13 (1942) 400-409
32. Zio E. A study of the bootstrap method for estimating the accuracy of artificial neural networks in predicting nuclear transient processes. IEEE Transaction of Nuclear Science 53 3 (2006)
33. Zio E., and Di Maio F. Using order statistics and the bootstrap technique for quantifying thermal-hydraulic code uncertainties in the estimation of probabilistic safety margins. Science and Technology of Nuclear Installations (2008) 10.1155/2008/340164